Only unswitch loops with uniform conditions
Loop unswitching can be extremely harmful for a SIMT target. In case
if hoisted condition is not uniform a SIMT machine will execute both
clones of a loop sequentially. Therefor LoopUnswitch checks if the
condition is non-divergent.
Since DivergenceAnalysis adds an expensive PostDominatorTree analysis
not needed for non-SIMT targets a new option is added to avoid unneded
analysis initialization. The method getAnalysisUsage is called when
TargetTransformInfo is not yet available and we cannot use it here.
For that reason a new field DivergentTarget is added to PassManagerBuilder
to control the behavior and set this field from a target.
Differential Revision: https://reviews.llvm.org/D30796
llvm-svn: 298104
diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
index c3acd9f..842f395 100644
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -168,6 +168,7 @@
PGOInstrUse = RunPGOInstrUse;
PrepareForThinLTO = EnablePrepareForThinLTO;
PerformThinLTO = false;
+ DivergentTarget = false;
}
PassManagerBuilder::~PassManagerBuilder() {
@@ -307,7 +308,7 @@
// Rotate Loop - disable header duplication at -Oz
MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1));
MPM.add(createLICMPass()); // Hoist loop invariants
- MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3));
+ MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3, DivergentTarget));
MPM.add(createCFGSimplificationPass());
addInstructionCombiningPass(MPM);
MPM.add(createIndVarSimplifyPass()); // Canonicalize indvars
@@ -588,7 +589,7 @@
MPM.add(createCorrelatedValuePropagationPass());
addInstructionCombiningPass(MPM);
MPM.add(createLICMPass());
- MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3));
+ MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3, DivergentTarget));
MPM.add(createCFGSimplificationPass());
addInstructionCombiningPass(MPM);
}